# Single-Shot Refinement Neural Network for Object Detection

arXiv: https://arxiv.org/abs/1711.06897 · HTML: https://mlsanity.com/paper/1711.06897/

## Key facts

- Cited by 129 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2017.

## Built on by (most cited first, 30 of 129)

- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Accelerating DETR Convergence via Semantic-Aligned Matching](https://mlsanity.com/paper/2203.06883/) (2022)
- [Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark](https://mlsanity.com/paper/2206.13996/) (2022)
- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [AO2-DETR: Arbitrary-Oriented Object Detection Transformer](https://mlsanity.com/paper/2205.12785/) (2022)
- [Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation](https://mlsanity.com/paper/2208.00219/) (2022)
- [Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation](https://mlsanity.com/paper/2103.08273/) (2021)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [NeRF-RPN: A general framework for object detection in NeRFs](https://mlsanity.com/paper/2211.11646/) (2022)
- [Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation](https://mlsanity.com/paper/2103.11731/) (2021)
- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations](https://mlsanity.com/paper/2104.10824/) (2021)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection](https://mlsanity.com/paper/2312.12664/) (2023)
- [Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism](https://mlsanity.com/paper/2301.10051/) (2023)
- [Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding](https://mlsanity.com/paper/2311.15206/) (2023)
- [One-Stage Cascade Refinement Networks for Infrared Small Target Detection](https://mlsanity.com/paper/2212.08472/) (2022)
- [SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.03150/) (2021)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention](https://mlsanity.com/paper/2203.03483/) (2022)
- [Video Relation Detection via Tracklet based Visual Transformer](https://mlsanity.com/paper/2108.08669/) (2021)
- [RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection](https://mlsanity.com/paper/2109.11906/) (2021)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)

## Abstract (arXiv)

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. RefineDet consists of two inter-connected modules, namely, the anchor refinement module and the object detection module. Specifically, the former aims to (1) filter out negative anchors to reduce search space for the classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes the refined anchors as the input from the former to further improve the regression and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO demonstrate that RefineDet achieves state-of-the-art detection accuracy with high efficiency. Code is available at https://github.com/sfzhang15/RefineDet